LongCat-Audio-Codec Open Source: An Extremely Low-Bitrate Audio Codec for Large Speech Models
I. Summary LongCat-Audio-Codec is an open-source audio codec solution developed by the Meituan LongCat team, optimized for the Speech Large Scale Mode...
I. Summary LongCat-Audio-Codec is an open-source audio codec solution developed by the Meituan LongCat team, optimized for the Speech Large Scale Mode...
I. Summary Qwen3Guard is an open-source security protection system launched by the Alibaba Cloud Qwen team, designed to improve the security of large ...
I. Summary HunyuanImage 3.0 is Tencent Hunyuan's open-source, native multimodal text-to-image model. It utilizes a MoE architecture and transfusion ap...
I. Summary Hunyuan3D-Part is an open-source, component-level 3D shape generation and decomposition solution from Tencent Hunyuan. It consists of P3-SA...
I. Summary Qwen3-VL is an open-source vision-language model developed by the Alibaba Cloud Qwen team. It is designed for unified understanding and rea...
Qwen3-Omni combines multimodal AI with end-to-end reasoning: a single model unifies the input and output of text, images, audio, and video, balancing ...